Bump memory buffer

diff --git a/main.cpp b/main.cpp
index d28fc916bac156743e66b1f5dd77e280722e6028..2f47480698f1e932ecec27fb7236fdea62c13ca0 100644 (file)
--- a/main.cpp
+++ b/main.cpp
@@ -529,7 +529,7 @@ bool llama_eval(
 
     const int d_key = n_embd/n_head;
 
-    static size_t buf_size = 256u*1024*1024;
+    static size_t buf_size = 512u*1024*1024;
     static void * buf = malloc(buf_size);
 
     if (mem_per_token > 0 && mem_per_token*N > buf_size) {